Jumprope
AI-powered fitness app delivering personalized workout experiences
PRODUCT DESIGN LEAD | RESEARCH-DRIVEN DESIGN, PERSONALIZATION
Imagine starting a new fitness journey, eager to make progress, but traditional workout apps lock you into rigid routines that don’t account for your recovery, motivation, or changing fitness levels. You push through, but the workouts don’t adapt when you feel fatigued, recover faster than expected, or need modifications for an injury. Progress feels unpredictable, and motivation starts to wane.
Jumprope set out to change that. As an AI-driven fitness app, it provides personalized, adaptive workouts that evolve in real-time based on user performance, recovery needs, and motivation levels. Unlike static fitness programs, Jumprope learns from each workout, making smart adjustments to keep training engaging, effective, and accessible.
My challenge? To refine how users engaged with AI-driven modifications, ensuring that personalized plans and workout adjustments were easy to understand, actionable, and seamlessly integrated into the training experience.
My Role
I worked closely with the app’s owner, who served as both the developer and personal trainer, to refine how users interacted with AI-generated modifications and personalized training plans. My role included conducting usability testing, identifying pain points, and improving how AI adjustments were presented to ensure users could easily navigate modifications and apply their training plans effectively.
Challenge
Users needed a clear way to understand and apply AI-driven workout modifications, but many found the reasoning behind adjustments unclear, making it harder to trust and engage with their training plans. The system adapted workouts based on user performance, recovery needs, and motivation levels, yet users struggled to see why changes were made or how to implement them. The challenge was to simplify how modifications were presented so users could quickly adjust their training without breaking their flow.
Outcome
Usability testing revealed that users often skipped AI-driven modifications because they weren’t sure how or why adjustments were being made. I refined how these changes were communicated, ensuring users could immediately see the connection between their performance, recovery, and personalized recommendations.
Working closely with the app’s owner, I refined how AI-driven adjustments were presented, ensuring users understood why changes were made and how they aligned with their goals. Early testing indicated that these improvements made individualized plans easier to follow, increasing user confidence in AI-driven training recommendations.
Execution
Usability testing revealed that users needed clearer explanations of why their workouts were being modified. To address this, I collaborated with the app’s owner to refine how AI-driven insights were displayed. I conducted multiple test sessions where participants reviewed their customized plans, providing feedback on where explanations felt unclear or overwhelming.
Insights from testing led to refinements such as more intuitive explanations of AI-driven modifications, a clearer link between recovery and workout adjustments, and better placement of adaptive training recommendations to ensure users engaged with their plans confidently. I iterated on these improvements in collaboration with the app’s owner, ensuring the system adapted seamlessly to different fitness levels and user needs.
Impact
Jumprope was tested with a group of users in a controlled environment, providing key insights into how AI-driven fitness adjustments could improve engagement. Test users reported that the ability to modify workouts in real time made sessions feel more personalized and adaptable.
Usability feedback indicated that the progressive AI-driven approach made the experience more intuitive, reinforcing the effectiveness of balancing automation with user control. These insights shaped further refinements to enhance trust in AI-generated recommendations.
Reflection + Key Takeaways
This project reinforced the importance of transparency in AI-driven interactions. While automation can improve experiences, maintaining clarity and user control is key to building trust.
By bridging UX, AI, and product strategy, I helped create an experience where AI worked with users rather than dictating their workouts—further strengthening my expertise in adaptive systems and human-AI interaction. The insights gained from testing helped refine how AI recommendations are surfaced, making them feel intuitive and trustworthy for future iterations.
